International Business Machines Corporation

Vanessa Lopez Garcia

Marco Luca Sbodio

Natalia Mulligan

Joao H Bettencourt-Silva

Gabriele Picco

Thanh Lam Hoang

Theodora Brisimi

Akihiro Kishimoto

Radu Marinescu

Spyros Kotoulas

Lam Nguyen

Dzung Tien Phan

Valentina Rho

Elizabeth Daly

Pierpaolo Tommasi

Yufang Hou

Charles Arthur Jochim

Aris Gkoulalas-Divanis

Sebastian Lehrig

John Segrave-Daly

Ramon Fernandez Astudillo

Young-Suk Lee

Fabrizio Cucci

Denisa Claudia Moga

The present inventive concept provides for a method for automated decision modelling from text including obtaining a text corpus including a policy. Terms and syntax are identified within the text corpus related to the policy. Sentence similarities and co-references based on the terms and syntax are identified. Discourse and sentence level semantic parsing is performed based on the terms and the sentence similarities and the co-references using machine learning. A decision model template is generated based on the discourse and semantic parsing, and the decision model template is transformed into an automated decision model.

Automated decision modelling from text

Software that performs the following operations: (i) receiving a set of graph predictions corresponding to an input text, where graph predictions of the set of graph predictions are generated by different respective machine learning models; (ii) blending the graph predictions of the set of graph predictions to generate a plurality of candidate blended graphs, where nodes and edges of the candidate blended graphs have respective selection metric values, generated using a selection metric function, that meet a minimum threshold; and (iii) selecting as an output blended graph a candidate blended graph of the plurality of candidate blended graphs having a highest total combination of selection metric values among the plurality of candidate blended graphs.

Blending graph predictions

Embodiments are provided for unsupervised learning of domain specific knowledge graph from textual data and language generation from knowledge graph via reinforcement learning in a computing system by a processor. Unstructured data is automatically parsed into one or more knowledge graphs based on the unstructured data and a list of candidate relations using a first machine learning model. Text data is generated from the one or more knowledge graphs using a second machine learning model.

Providing a semantic encoding and language neural network

Embodiments are provided for generating a reasonable language model learning for text data in a knowledge graph in a computing system by a processor. One or more data sources and one or more triples may be analyzed from a knowledge graph. Training data having one or more candidate labels associated with one or more of the triples may be generated. One or more reasonable language models may be trained based on the training data.

Reasonable language model learning for text generation from a knowledge graph

A computer-implemented method for automatically generating a semantic vector representation of a relation between a specific set of entities in natural language text is provided. The method may include, in response to receiving a text segment comprising a set of entities, automatically parsing the text segment into an abstract meaning representation (AMR) graph comprising nodes representing the set of entities. The method may further include extracting a number of minimum Steiner trees from the AMR graph, and wherein each Steiner tree comprises a minimum amount of edges between the nodes corresponding to a first entity and at least one second entity. The method may further include using a trained graph neural network (GNN) to determine vector embeddings for the minimum Steiner trees. The method may further include aggregating the vector embeddings to generate the semantic vector representation of the relation between the specific set of entities.

Generating semantic vector representation of natural language data

Various embodiments are provided for intelligent application of operational rules to operational data in a computing environment by a processor. One or more operational rules may be extracted and formalized from a knowledge graph, a domain knowledge, or a combination thereof describing one or more operational policies and conditions. The one or more operational rules may be applied to operational data to identify and filter non-compliant operational data.

Intelligent learning and application of operational rules

A system and method for analyzing and explaining the temporal evolution of policies. The analysis of the temporal evolution of policies includes determining semantically related changes in the text of the corresponding policies over time and across the different versions of the (two or more) policy documents. An explanation of the temporal evolution of policies is provided consisting of human interpretable information relating each change to one or more events and/or contextual data. A next steps policy change is also suggested that includes a set of policy conditions based on potential future changes of similar policies and contextual data and event data. The suggestions are related to the policy relevant to the target cohort or individual. The system adapts machine learned models by receiving user feedback provided on an analysis of the correctness of the temporal evolution of policies, corresponding explanations and suggestions of the next actions.

Analyzing and explaining a temporal evolution of policies and suggesting next steps

Systems, computer-implemented methods, and computer program products to facilitate contextual comparison of semantics in conditions of different policies are provided. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a comparison component that contextually compares semantics of conditions in policy data of different policies based on a feature of at least one entity. The computer executable components further comprise a contextualization component that employs a model to provide a contextual explanation of how a first condition in first policy data of a first policy is semantically different from a second condition in second policy data of a second policy based on the feature of the at least one entity.

Contextual comparison of semantics in conditions of different policies

Systems, computer-implemented methods and/or computer program products that facilitate answering questions that involve mathematical computations are provided. In one embodiment, a computer-implemented method comprises: transforming, by a system operatively coupled to a processor, a natural language query into a first logical representation and extrinsic knowledge into a second logical representation relevant to the natural language query; merging, by the system, the first logical representation and the second logical representation into a third logical representation; and generating, by the system, answers for the natural language query based on processing of the third logical representation.

Facilitating answering questions involving reasoning over quantitative information

Embodiments for intelligent generation of customized questions or questionnaires by a processor. One or more customized questions or questionnaires may be generated according to a user profile, similar profiles of alternative users, one or more historical interactions with the alternative users, one or more goals defined by a domain experts, domain knowledge, historical questions or questionnaires, or a combination thereof using a machine learning operation.

Intelligent generation of customized questionnaires

Various embodiments are provided for providing intelligent policy coverage optimization in a computing environment by a processor. One or more policy coverage gaps in one or more operational rules defined by one or more rules, policies, or a combination thereof and associated with one or more non-compliant policy claims associated with the one or more policy coverage gaps may be identified. The one or more policy coverage gaps may be ranked according to one or more selected criteria.

Intelligent policy covery gap discovery and policy coverage optimization

Techniques are described for extracting structured information from unstructured documents based on validation of the structured information as applied to a domain problem associated with the unstructured documents. In one embodiment, a computer program product for automated information extraction is provided. The computer program product comprising a computer readable storage medium having program executable by a processing component to cause the processing component to extract structured candidate interpretations of a rule from unstructured information that defines a plurality of rules intended to control operations of a system, and determine measures of validity of the structured candidate interpretations based on application of the candidate policy interpretations to historical operational data for the system that represents operations performed by the system. The measures of validity respectively can represent degrees to which the historical operational data reflects operation of the system in accordance with the structured candidate interpretations.

Extracting structured information from unstructured data using domain problem application validation

Embodiments for intelligent learning for explaining anomalies to a user by a processor. One or more anomalous records may be identified in a knowledge base. A list of ranked candidate explanations may be generated for the one or more anomalous records. An active learning dialog may be initiated with one or more users to increase accuracy of the knowledge base, a domain knowledge, and each of the ranked candidate explanations.

Intelligent learning for explaining anomalies

Embodiments for intelligent recommendation of useful medical actions to a user by a processor. One or more useful medical actions may be cognitively recommended with evidence in support thereof for impacting a health state of a user according to historical data collected from one or more data sources, one or more user profiles, a domain knowledge, feedback data, or a combination thereof. The one or more useful medical actions may be ranked according to a scoring criteria, the domain knowledge, the historical data, a set of rules, previously recommended medical actions, or a combination thereof.

Growing community of inventors

Dublin, Ireland

Vanessa Lopez Garcia